README_ACC.md

README file for PRACE Accelerator Benchmark Code PFARM (stage EXDIG, program RMX95)
===================================================================================
Author: Andrew Sunderland (a.g.sunderland@stfc.ac.uk).

The [code download](https://www.dropbox.com/sh/dlcpzr934r0wazy/AABlphkgEn9tgRlwHY2k3lqBa?dl=0
) should contain the following directories:


```
benchmark/RMX_HOST: RMX source files for running on Host or KNL (using LAPACK or MKL)
benchmark/RMX_MAGMA_GPU: RMX source for running on GPUs using MAGMA
benchmark/lib: 
benchmark/run: run directory with input files
benchmark/xdr: XDR library src files
```

The code uses the eXternal Data Representation library (XDR) for cross-platform
compatibility of unformatted data files. The XDR source files are provided with this code bundle.
It can be obtained from various sources, including
http://people.redhat.com/rjones/portablexdr/


Compilation
***********
Installing MAGMA (GPU Only)
---------------------------
Download MAGMA (current version magma-2.2.0)  from http://icl.utk.edu/magma/
Install MAGMA : Modify the make.inc file to indicate your C/C++
compiler, Fortran compiler, and where CUDA, CPU BLAS, and 
LAPACK are installed on your system. Refer to MAGMA documentation for further details

Install XDR
-----------
build XDR library: 
update DEFS file for your compiler and environment

```shell
$> make
```

Install RMX_HOST
----------------
Update DEFS file for your setup, ensuring you are linking to a LAPACK or MKL library.
This is usually facilitated by e.g. compiling with `-mkl=parallel` (Intel compiler) or loading the appropriate library modules. 

```shell
$> cd RMX_HOST
$> make
```

Install RMX_MAGMA_GPU 
---------------------
Update DEFS file for your setup:
 - Set MAGMADIR, CUDADIR and OPENBLASDIR environment variables
 - Updating the fortran compiler and flags in DEFS file.

```shell
$> cd RMX_MAGMA_GPU
$> make
```


Run instructions
****************

Run RMX
-------

The RMX application can be run by running the executable `rmx95`
For the FEIII dataset, the program requires the following input files to reside in the same directory as the executable:

```
phzin.ctl
XJTARMOM
HXJ030
```

These files are located in `benchmark/run`
A guide to each of the variables in the namelist in phzin.ctl can be found at:
https://hpcforge.org/plugins/mediawiki/wiki/pfarm/images/9/99/Phz_rep.pdf
However, it is recommended that these inputs are not changed for the benchmark code and
problem size, runtime etc, are controlled via the environment variables listed below.

A typical PBS script to run the RMX_HOST benchmark on 4 KNL nodes (4 MPI tasks with 64 threads per MPI task) is listed below:
Settings will vary according to your local environment.

```shell
#PBS -N rmx95_4x64
#PBS -l select=4
#PBS -l walltime=01:00:00
#PBS -A my_account_id

cd $PBS_O_WORKDIR
export OMP_NUM_THREADS=64

aprun -N 1 -n 4 -d $OMP_NUM_THREADS ./rmx95
```

Run-time environment variable settings
--------------------------------------
The following environmental variables that e.g. can be set inside the script allow the H sector matrix 
to easily change dimensions and also allows the number of sectors to change when undertaking benchmarks.
These can be adapted by the user to suit benchmark load requirements e.g. short vs long runs.
Each MPI Task will pickup a sector calculation which will then be distributed amongst available threads per node (for CPU and KNL) or offloaded (for GPU).
The distribution among MPI tasks is simple round-robin.
 
 - `RMX_NGPU` : refers to the number of shared GPUs per node (only for RMX_MAGMA_GPU)
 - `RMX_NSECT_FINE` : sets the number of sectors for the Fine region. 
 - `RMX_NSECT_COARSE` : sets the number of sectors for the Coarse region. 
 - `RMX_NL_FINE` : sets the number of basis functions for the Fine region sector calculations. 
 - `RMX_NL_COARSE` : sets the number of basis functions for the Coarse region sector calculations. 

**Notes**:
For a representative setup for the benchmark datasets:

 - `RMX_NL_FINE`  can take values in the range 6:25
 - `RMX_NL_COARSE`  can take values in the range 5:10 
 - For accuracy reasons, `RMX_NL_FINE` should always be great than `RMX_NL_COARSE`. 
 - The following value pairs for `RMX_NL_FINE` and `RMX_NL_COARSE` provide representative calculations:

```
12,6
14,8
16,10
18,10
20,10
25,10
```

If `RMX_NSECT` and `RMX_NL` variables are not set, the benchmark code defaults to:

```
RMX_NSECT_FINE=5
RMX_NSECT_COARSE=20
RMX_NL_FINE=12
RMX_NL_COARSE=6
```

The Hamiltonian matrix dimension will be output along 
with the Wallclock time it takes to do each individual DSYEVD call.

Performance is measured in Wallclock time and is displayed 
on the screen or output log at the end of the run.